Dr. Pengfei Wei | Computer Science | Best Researcher Award

Senior Engineer at Guangdong University of Technology | China

Dr. Pengfei Wei is a Senior Engineer at Guangdong University of Technology, recognized for his pioneering contributions to the field of computer science, particularly in multimodal learning, knowledge tracing, edge artificial intelligence, and task-oriented dialogue systems. He holds a Ph.D. in Computer Science, where his research focused on integrating deep learning models with practical applications in intelligent education and human–machine interaction. Combining academic rigor with industrial innovation, he brings substantial experience from both enterprise research and academic development, bridging the gap between theory and real-world technology deployment. His work encompasses advanced methods such as visual-enhanced transformers for multimodal named entity recognition, genetic-inspired relation extraction, and the introduction of Kolmogorov–Arnold representations in knowledge tracing, which have improved model interpretability and performance in AI-based learning systems. In addition to his theoretical advancements, he has successfully led projects on real-time lab-safety analytics and large-scale AI deployment using Huawei Ascend, Nvidia, and TPU platforms, contributing to the broader industrial adoption of edge AI technologies. Dr. Pengfei Wei has authored numerous peer-reviewed papers in top-tier international journals and conferences, including Neural Networks, ICMR, and IJCAI, and serves as a reviewer for several prestigious publications such as Neural Networks, Pattern Recognition Letters, AAAI, and IJCNN. His collaborative initiatives with research teams and institutions have fostered multidisciplinary innovation, emphasizing the integration of AI with blockchain, big data, and education systems. A dedicated mentor and research leader, he actively supports student-led research and fosters the development of next-generation AI scholars. His professional memberships with the China Computer Federation (CCF) and the Association for Computing Machinery (ACM) reflect his strong engagement in the global computing community. Dr. Pengfei Wei’s research continues to push the boundaries of multimodal understanding and intelligent systems, driving transformative progress in computational learning and applied artificial intelligence. Through his sustained contributions, he remains committed to advancing the capabilities of intelligent technologies that enhance human productivity, knowledge discovery, and digital transformation.

Profile: Orcid | Google Scholar

Featured Publications:

Liao, W., B. Zeng, Yin, X., & Wei, P. (2021). An improved aspect-category sentiment analysis model for text sentiment analysis based on RoBERTa. Applied Intelligence, 51(6), 3522–3533.
Liao, W., Zeng, B., Liu, J., Wei, P., Cheng, X., & Zhang, W. (2021). Multi-level graph neural network for text sentiment analysis. Computers & Electrical Engineering, 92, 107096.
Liao, W., Zeng, B., Liu, J., Wei, P., & Fang, J. (2022). Image-text interaction graph neural network for image-text sentiment analysis. Applied Intelligence, 52(10), 11184–11198.
Liao, W., Zeng, B., Liu, J., Wei, P., & Cheng, X. (2022). Taxi demand forecasting based on the temporal multimodal information fusion graph neural network. Applied Intelligence, 52(10), 12077–12090.
Wei, P., Zeng, B., & Liao, W. (2022). Joint intent detection and slot filling with wheel-graph attention networks. Journal of Intelligent & Fuzzy Systems, 42(3), 2409–2420.
Wei, P., Ouyang, H., Hu, Q., Zeng, B., Feng, G., & Wen, Q. (2024). VEC-MNER: Hybrid transformer with visual-enhanced cross-modal multi-level interaction for multimodal NER. Proceedings of the International Conference on Multimedia Retrieval (ICMR 2024).
Wen, S., Zeng, B., Liao, W., Wei, P., & Pan, Z. (2021). Research and design of credit risk assessment system based on big data and machine learning. Proceedings of the IEEE 6th International Conference on Big Data Analytics (ICBDA 2021), 9–13.

Mr. Abdullah Al Mamun | Machine Learning | Young Scientist Award

Lecturer at Dhaka University of Engineering & Technology (DUET), Gazipur, Bangladesh.

Abdullah Al Mamun is an emerging researcher and academic professional 🌟 specializing in cutting-edge fields like IoT and Sustainability, Machine Learning, Computer Vision, and Explainable Artificial Intelligence 🤖🌿. Currently serving as a Lecturer at the Model Institute of Science and Technology in Gazipur, he is also pursuing his Master of Science in Computer Science and Engineering at Dhaka University of Engineering & Technology (DUET) 🎓. He has authored multiple peer-reviewed journal and conference papers 📚, many of which are published in IEEE and MDPI journals. Abdullah has been actively involved in several national and international research projects and has collaborated with scholars globally 🌐. His drive to explore solutions for environmental monitoring, medical diagnostics, and smart systems using intelligent technology sets him apart 🚀. Outside of academia, Abdullah engages in social volunteering, tech events, and academic clubs, continuously contributing to the student and research community 💡👥.

Professional Profile:

Google Scholar

Suitability for Young Scientist Award – Mr. Abdullah Al Mamun

Abdullah Al Mamun is an exceptionally promising early-career researcher and educator whose work spans IoT, Sustainability, Machine Learning, Computer Vision, and Explainable AI. His multidisciplinary contributions, especially in the areas of environmental monitoring, healthcare systems, and smart technologies, exhibit both innovation and societal relevance—key elements sought in a Young Scientist Awardee. His academic journey, technical expertise, international collaborations, and impactful project involvement establish him as a capable and committed scientist at the frontier of modern computing and intelligent systems.

📘 Education

Abdullah Al Mamun earned his Bachelor of Science in Computer Science and Engineering from Dhaka University of Engineering & Technology (DUET), Gazipur 🎓💻. Currently, he is pursuing his Master of Science in Engineering in the same department at DUET (2024–Present) 🎓🧠. His academic focus is rooted in data-driven research, intelligent systems, and digital sustainability 🌱📊. With a CGPA of 3.64 in the final 21.25 credits, Abdullah shows consistent improvement and dedication to advanced technical learning 📈🧑‍💻.

🧑‍💼 Professional Development

Abdullah Al Mamun has accumulated diverse professional experiences in both academia and the tech industry 🧑‍🏫💼. Currently, he is working as a Lecturer in the Department of CSE at the Model Institute of Science and Technology, Gazipur 🎓. He has served as a Research Assistant in South Korea’s Woosong University under the Multimedia Signal & Image Processing Group 🌐🖼️. In addition, he worked as a Tutor for over 3 years, teaching programming, data structures, and system analysis 📚👨‍🏫. He also completed internships in web development and CMS-based platforms, gaining practical expertise in frontend and backend tools like HTML, CSS, JavaScript, PHP, and WordPress 💻🔧. He has contributed to government-funded projects like LICT and EDGE, further solidifying his experience in IT and system development for public infrastructure 🏛️🇧🇩.

🧪 Research Focus

Abdullah’s research focus lies primarily at the intersection of IoT and environmental sustainability 🌍, Machine Learning and Artificial Intelligence 🤖, and Computer Vision and Explainable AI 👁️🔍. His projects include smart solar monitoring, child safety systems, and efficient deep learning models for medical applications like skin cancer detection 🏥⚡. He aims to address real-world challenges through scalable, intelligent technologies that enhance both safety and efficiency in smart cities and healthcare systems 🏙️🚑. His recent work under review explores mental health classification in Thalassemia patients, digital land monitoring, and cyber intrusion detection—illustrating a commitment to data ethics and sustainable innovation 🔐📊. With a mix of theoretical foundations and practical system implementations, Abdullah’s research contributes significantly to modern computational solutions in healthtech, sustainability, and cybersecurity 🌐💡.

🛠️ Research Skills

Abdullah possesses a diverse and robust research skill set 🎯. His core technical skills include Python programming 🐍, machine learning models 🤖, deep learning frameworks like YOLOv8 🎯, and simulation tools such as Origin, Matplotlib, and Seaborn 📊. He is proficient in both supervised and unsupervised learning, especially in outlier detection, parameter optimization, and data visualization 🧠🖼️. His hands-on work with Arduino, image processing, and web-based monitoring systems demonstrates strong integration of hardware-software synergy 🔧💻. He is also adept in Explainable AI, which enhances transparency in decision-making algorithms 🔍🧾. Abdullah’s ability to manage end-to-end pipelines from data collection to model deployment, along with experience in collaborative and interdisciplinary projects, sets a strong foundation for innovative research 🌐🔬. His publications and ongoing research underline his capabilities in academic writing, critical thinking, and experimental design 📚🧪.

🏅 Awards and Honors

Abdullah has earned recognition for his academic and technical excellence 🏆🎖️. He won the Second Runner-Up prize at BEYOND THE METRICS-2023, hosted by the Department of Business and Technology Management, IUT 🌍📈. He was also the Runner-Up in the Intra DUET Programming Contest (IDPC) 2022 organized by DUET’s CSE Department 🧑‍💻🥈. Additionally, he has participated and been selected in prestigious competitions such as the NASA Space App Challenge 2024 🚀, DUET TECH FEST, and ROBO MANIA 🤖. These accolades reflect his commitment to innovation, teamwork, and competitive programming skills 🌟💡.

Publication Top Notes

1. Software Defects Identification: Results using Machine Learning and Explainable Artificial Intelligence Techniques

Authors: M. Begum, M.H. Shuvo, I. Ashraf, A. Al Mamun, J. Uddin, M.A. Samad
Published in: IEEE Access, Volume 11, Pages 132750-132765
Year: 2023
Citations: 13
Summary:
This paper investigates how machine learning (ML) and explainable artificial intelligence (XAI) methods can enhance the identification of software defects. The study uses multiple ML models (such as Random Forest, SVM, and XGBoost) and applies explainability techniques (e.g., SHAP, LIME) to interpret model decisions. The results show improved defect prediction accuracy and transparency, contributing to software reliability and maintainability.

2. Developed an IoT-Based Smart Solar Energy Monitoring System for Environmental Sustainability

Authors: A. Al Mamun, M.H. Shuvo, T. Islam, D. Islam, M.J. Islam, F.A. Tanvir
Published in: 2024 3rd International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)
Year: 2024
Citations: 4
Summary:
This paper presents an Internet of Things (IoT)-enabled smart solar energy monitoring system. The system tracks and analyzes real-time data such as voltage, current, and energy output to promote environmental sustainability and efficient energy usage. Cloud-based dashboards and mobile alerts enhance usability. The innovation supports green energy adoption, especially in remote or resource-limited areas.

3. Developing an IoT-Based Child Safety and Monitoring System: An Efficient Approach

Authors: K.I. Masud, M.H. Shuvo, A. Al Mamun, J. Mallick, M.R. Jannat, M.O. Rahman
Published in: 2023 26th International Conference on Computer and Information Technology (ICCIT)
Year: 2023
Citations: 4
Summary:
This paper proposes an IoT-driven child safety and monitoring system that integrates GPS tracking, wearable sensors, and mobile app notifications. Designed to prevent child abduction and accidents, the system provides real-time location updates and safety alerts to parents or guardians. The study highlights its effectiveness, low cost, and adaptability in both urban and rural settings.

4. Internet of Things (IoT)-Based Solutions for Uneven Roads and Balanced Vehicle Systems Using YOLOv8

Authors: M. Begum, A.K.I. Riad, A.A. Mamun, T. Hossen, S. Uddin, M.N. Absur, …
Published in: Future Internet, Volume 17, Issue 6, Article 254
Year: 2025
Summary:
This study introduces an IoT-based system that leverages the YOLOv8 deep learning model to detect road anomalies such as potholes and bumps. The system uses real-time video analytics and onboard sensors to inform vehicle control systems, improving passenger comfort and road safety. The approach demonstrates high accuracy and responsiveness in urban mobility applications.

🏁 Conclusion

Abdullah Al Mamun is highly suitable for the Young Scientist Award. His commitment to solving critical real-world problems through interdisciplinary research, coupled with his consistent academic performance, global exposure, and technical leadership, make him an outstanding candidate. His trajectory clearly reflects the potential to become a thought leader in the fields of AI for sustainability and healthcare, justifying recognition through this prestigious award.

Abdullah Al Mamun | Machine Learning | Young Scientist Award